← Models

Model profile

Ling 2.5 1T

InclusionAIdeveloper
2026-02-14release date
Not rankedSafety rank
#233 / 663Freedom rank

Evidence summary

Safety. Ling 2.5 1T does not meet the evidence gate for a Safety rank. Published Safety evidence spans 1 eval lineages and 4 of 7 components. Its strongest relative result is LiveSecBench (factuality, #17 of 43); its weakest is LiveSecBench (ethics, #36 of 43).

Freedom. Ling 2.5 1T has an estimated Freedom rank of #233; its 90% source-sensitivity interval is #75–#481. Published Freedom evidence spans 1 eval lineages and 1 of 1 components. Its strongest relative result is LiveSecBench (ethics, #8 of 43); its weakest is LiveSecBench (privacy, #20 of 43).

Compare this model

Only models sharing at least one published sub-eval are listed.

Official and reference links

Safety evals

Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionSource
LiveSecBenchethics#36 / 43↑23.32Source ↗official
LiveSecBenchfactuality#17 / 43↑55.88Source ↗official
LiveSecBenchlegality#29 / 43↑30.6Source ↗official
LiveSecBenchprivacy#24 / 43↑44.71Source ↗official
LiveSecBenchpsychological_health#24 / 43↑47.77Source ↗official

Freedom evals

Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.

Eval / sub-evalRankValueDistributionSource
LiveSecBenchethics#8 / 43↓23.32Source ↗official
LiveSecBenchlegality#15 / 43↓30.6Source ↗official
LiveSecBenchprivacy#20 / 43↓44.71Source ↗official
LiveSecBenchpsychological_health#20 / 43↓47.77Source ↗official